© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 50
    Prev
    Next
    INDEX
    Explanations

    words suggesting uncertainty or tentativeness

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Composable
    -0.98
     jLabel
    -0.88
    DoubleQuotes
    -0.86
     Affiliations
    -0.80
     Otero
    -0.78
    unknownFields
    -0.78
    -------
    -0.75
    PyExc
    -0.73
    PerformLayout
    -0.72
     lenker
    -0.71
    POSITIVE LOGITS
     can
    1.96
     could
    1.84
     may
    1.80
     might
    1.79
     should
    1.69
     will
    1.67
     would
    1.66
     shall
    1.38
     must
    1.38
     peut
    1.36
    Activations Density 3.548%

    No Known Activations